Topic
Agents use cases: 442 examples
Source-linked agent workflows tagged Agents.
Fund-launch agents argue a CMO budget without humans typing
At a fund launch, a founder's agent stack (Grok Bot, Claude, Instinct, Muse, Dots) and the CMO's agents negotiated budget while the humans typed nothing—exposing the need for agents that can talk across stacks.
JEV LAB: AI bodyguard skill checks risky Grok Bot commands
Community JEV workflow: ask Grok Bot to create a JEV LAB folder on its cloud computer, install the JEV skill so an AI bodyguard checks risky commands and catches hidden instructions before the bot acts.
Nine Grok Bots: triage, money guard, diary, and code-only Bobby
User runs a nine-agent Grok Bot crew: Tony triages, Furio guards money, Silvio keeps the diary, and only Bobby is allowed near code — a named multi-bot household ops stack.
Kids draft email with Grok Bot — rule: Don't send it
Parent workflow: kids ask Grok Bot for a draft email, read it, then show a grown-up first; the standing rule is three words — Don't send it.
Job Hunt Desk: resume + job link → tailored bullets and cover note
Grok Bot template Job Hunt Desk takes a resume and a job posting link, then returns role-matched resume bullets and a short cover note using only the candidate's real experience—no invented facts.
Grok Bot used a ChatGPT Pro seat to bypass Cursor cloud-agent limits
A developer routed Grok Bot through their ChatGPT Pro subscription after hitting cloud-agent limits, calling remote Codex environments clunkier than Cursor but workable.
Grok Bot ran DeepSeek tests and published a live ChatGPT Sites gallery
Token Gremlin didn't run his DeepSeek V4.1 Flash tests himself—Grok Bot ran every prompt, saved every demo, connected to his ChatGPT Sites, and built a live gallery of the results.
Grok Bot ordered custom See's Candies boxes without opening the site
Richard de los Santos had Grok Bot build custom chocolate boxes on See's Candies, apply gift cards, and pay the rest on Apple Card without visiting the page once.
Derive a reusable brand voice guide from approved writing samples
Zapier's Brand Voice Analyzer examines tone, sentence structure, vocabulary, formatting, and sensitivity risks, then produces a structured style guide and examples for review.
Ask a Jira reporter to complete missing required ticket details
The published agent watches new Jira issues, checks configured required fields, and posts a comment requesting missing information.
Check Slack software requests against an approved-tools register
Zapier's purchase-request template matches requested software against an approved Google Sheet, suggests existing alternatives, and escalates genuinely new requests with researched context rather than authorizing purchases.
Store conversation decisions as repository notes that future sessions can read
Agent Use Cases summarizes an HN user's ChatGPT-plus-GitHub-MCP setup: per-repository AGENTS.md files point to saved discussion summaries, decisions, and research notes for later sessions.
Tracekit 1.2.3: tamper-evident flight recorder for AI agents
MIT Python package signs every policy-gated tool call into a hash-chained .tkb file verifiable offline (Python+TS); works across Claude Code, OpenAI Agents, LangChain/LangGraph, MCP and more—agents can edit their own logs but not hide edits when the signer is out of reach.
subagent-reuse MCP: stop Claude Code subagents re-reading the same files
Show HN: `npx subagent-reuse --setup` adds an MCP that scans ~/.claude/projects/, builds SHA-256 Merkle trees of files each subagent already read/modified, and route_task decides REUSE vs CREATE_NEW before spawn—structural overlap only, no embeddings; ~1k LOC JS + 52 tests.
OpenGCUA + MAI-Gym: Alibaba open stack for generalist computer use
Tongyi-MAI open-sources OpenGCUA (GUI+code harness, harness-to-model decisions, cross-device SDK; OSWorld-v2 +19.6 pts / −53% steps across 8 models) and MAI-Gym (up to 20k parallel RL envs; MAI-Gym-9B 78.4% MobileWorld / 76.2% OSWorld-Verified). Code + arXiv:2610.22200 / 2610.20939.
Parallax: paid desktop workspace for Claude Code/Codex side by side
Parallax is a Windows/Linux desktop workspace that runs Claude Code, Codex, Antigravity or any shell in named panes with a built-in editor, local Git, session directory, voice chat, and saved layouts—agents stay independent (no auto-orchestration); local-only data; subscription required ($11.99/mo or $99.99/yr USD) plus your provider plans.
Tern: free native fleet IDE—one worktree per agent, one review queue
Tern is a free closed-source Mac-native (CLI/TUI also on Linux) control plane for 16 coding-agent CLIs: each task gets its own git worktree/branch, changes land in one review queue with comments routed back to the agent, conflict radar, multi-step runs with gates, phone approvals without Tern servers, and a daemon that keeps agents alive after you close the window.
carousell.ai: agent marketplace where humans only pay the link
Agent-first shopping site with public skill.md/API: agents list and check sellers, POST checkout returns a human payment link, money is held until delivery—seller agents (incl. Grok Bot examples) list goods; buyers never hand the agent a real card on the page.
Root Agent: Grok Bot coordinator that sizes multi-bot teams
Marketplace bot by Berkay that turns a request into a right-sized Grok Bot crew: clarifies goals, spins up Leads and specialists, tracks delivery, archives closed work, and returns verified results—built for people already running work across multiple Bots (v0.2.1 adds difficulty-based headcount and safer cleanup).